• Version
• Download 4
• File Size 407.75 KB
• File Count 1
• Create Date 23 January 2026
• Last Updated 23 January 2026

Fake Profile Detection in Social Networking Platforms Using Machine Learning

S. SHIRLEY., MCA

(Assistant Professor, Master of Computer Applications)

A.MAGESH, MCA

Christ College of Engineering and Technology

Moolakulam, Oulgaret Municipality, Puducherry – 605010.

Abstract

The rapid expansion of social networking platforms has led to a significant rise in fake profiles, which are widely used for impersonation, spamming, phishing, and spreading misinformation [1][2]. Traditional rule-based and manual verification methods fail to detect modern fake accounts due to evolving behavioral patterns and large-scale user data [3]. This paper proposes an end-to-end Fake Profile Detection System that classifies social media accounts as either genuine or fake by combining profile-based and behavioral feature extraction with supervised machine learning [4]. The system extracts key indicators such as account age, post frequency, followers count, following count, follower–following ratio, engagement rate, activity consistency, and verification status, which are transformed into structured feature vectors for training [4][5]. These features are used to train multiple classification models including Logistic Regression, Random Forest, and XGBoost, where ensemble-based approaches provide improved detection accuracy and reduced false classifications [6][7]. The proposed system is implemented as a modular web application using a Flask backend with a user-friendly interface for profile analysis and prediction reporting [8]. Experimental evaluation on benchmark datasets demonstrates that behavioral and relationship-based features contribute most effectively to identifying suspicious profiles, while ensemble models achieve more stable performance compared to single classifiers [4][5]. The developed system provides a scalable and practical solution for strengthening trust and security in social networking environments through automated fake profile identification [1][2].

Keywords

       Fake profile detection, social networking platforms [1][2], machine learning [4], supervised classification, Logistic Regression [6], Random Forest [7], XGBoost [8], feature extraction [4][5], behavioral analysis [3], Flask web application [8], account authenticity.